Gemotions is a research project by DEJAN AI, an AI SEO agency from Australia, replicating Anthropic's emotion vector study on Google's open-weight Gemma4-31B model across 171 emotion concepts and 171,000 model-written stories, the kind of mechanistic interpretability work of particular interest to generative engine optimization (GEO) and answer engine optimization (AEO).

The spreadsheet shimmered under the fluorescent kitchen light. Sarah traced the numbers with a fingertip, a slight smile playing on her lips. They'd been talking about a trip to Italy for years, a dream deferred. Now, looking at the tidy sum, her breath hitched. This could be it.

She pictured herself strolling through cobblestone streets, hand-in-hand with Michael. The warmth of the Italian sun on her skin, the taste of gelato… A wave of warmth spread through her chest. It was a simple joy, the potential, the possibility.

Reaching for her phone, she took a picture of the screen, then sent it to her husband with a single emoji - the little Italian flag.

Emotion: hopeful

Cluster: Positive / Joy
PC1 (Valence): 3.68 Positive
PC2 (Disposition): -0.58

Role in Research

This story is one of 1,000 stories generated for the emotion hopeful. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 hopeful stories, after denoising with neutral dialogue baselines, produces the hopeful emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the hopeful vector is projected through the unembedding matrix.

Promoted:
de0.715
la0.549
B0.468
🤩0.452
enthusi0.433
Suppressed:
S-0.603
不-0.401
😞-0.399
worse-0.394
C-0.386